Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2134 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.5919. Min Range: -4.5919

Max Act: 4.5919. Min Act: -0.0001

Data Index: 1232591 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.9268. Min Act: -0.0001

Data Index: 505653 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.7075. Min Act: -0.0000

Data Index: 504185 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.7536. Min Act: -0.0000

Data Index: 420800 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.6843. Min Act: -0.0000

Data Index: 921740 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.6497. Min Act: -0.0000

Data Index: 1311674 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.2789. Min Act: -0.0001

Data Index: 755476 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.2856. Min Act: -0.0000

Data Index: 1236152 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.3785. Min Act: -0.0001

Data Index: 984790 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.2955. Min Act: -0.0001

Data Index: 1260410 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.1905. Min Act: -0.0000

Data Index: 846971 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.3428. Min Act: -0.0001

Data Index: 710296 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.4547. Min Act: -0.0000

Data Index: 1059186 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.0166. Min Act: -0.0000

Data Index: 79248 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.0770. Min Act: -0.0000

Data Index: 403507 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.0237. Min Act: -0.0001

Data Index: 510925 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.0619. Min Act: -0.0001

Data Index: 1173731 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 4.5919. Min Range: -4.5919

Max Act: 3.0094. Min Act: -0.0000

Data Index: 519876 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 4.5919. Min Range: -4.5919

Max Act: 2.9565. Min Act: -0.0001

Data Index: 678707 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 4.5919. Min Range: -4.5919

Max Act: 2.8758. Min Act: -0.0001

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 153